International Journal of Advanced Mechatronic Systems (5 papers in press)

Regular Issues

• Resilient fuzzy SVM control design for nonlinear Markov jump cyber physical systems against replay attacks  
  by Maryam Fattahi 
  Abstract: This paper presents a novel control strategy framework using fuzzy support vector machine (FSVM) for enhancing the detection and resilience of nonlinear Markov jump cyber-physical systems (NMJCPS) under replay attacks. At first, an introduction to FSVM method is given. Then, dynamic of MJCPS with replay attack is presented. In such condition, resilient FSVM control mechanism for stabilisation of system in condition of abnormal behaviour due to replay attacks is proposed. The proposed new approach ensures system stability and performance during and after the attack. Simulation results demonstrate the effectiveness of the control design in mitigating the effects of replay attacks and maintaining system functionality.
  Keywords: fuzzy SVM control; nonlinear Markov jump cyber-physical systems; NMJCPS; replay attacks.
  DOI: 10.1504/IJAMECHS.2026.10075373
   
  
• A Gaussian-based adaptive control scheme for wireless power transfer systems using modified particle swarm optimisation  
  by Xudong Gao, Lihong Chen, Wenjie Cao, Qiang Yang 
  Abstract: In recent years, intelligent control schemes have gained prominence in wireless power transfer (WPT) systems, significantly influencing their time-domain performance. Most recent studies focus on global control strategies that employ a fixed set of controller parameters during operation. However, these strategies lack the capability to adaptively adjust parameters based on the system state, resulting in suboptimal responses. To address these limitations, this paper proposes a Gaussian-based adaptive control scheme for WPT systems. By integrating the Gaussian function into PWM-based SMC techniques, the controller can be dynamically adjusted in accordance with the system's behaviour, thereby enhancing system performance. Furthermore, the controller parameters are optimised using modified particle swarm optimisation for dynamical changes of the control system design, leading to further improvement of system performance. Furthermore, simulations are presented to prove the effectiveness of the proposed adaptive control scheme.
  Keywords: Gaussian adaptive technique; adaptive sliding mode control; modified particle swarm optimisation; wireless power transfer system.
  DOI: 10.1504/IJAMECHS.2026.10077252
   
  
• Detection from audio and text data features using modified score level fusion and improved deep convolutional neural network  
  by Janaswami Hymavathi, Chokka Anuradha 
  Abstract: Depression is a serious illness that requires prompt treatment to avoid negative impacts on a person's quality of life and general health. It is characterised by enduring feelings of melancholy and pessimism. Treatment options typically encompass psychotherapy, medication, or a combination designed for individual needs. Recognising the importance of early detection, this research introduces a depression detection model based on modified score level fusion-improved deep convolutional neural network, that utilises audio and text data features. The research methodology follows a systematic approach involving pre-processing, feature extraction, and depression detection process. Audio and text inputs undergo independent pre-processing and feature extraction using specialised techniques. The resulting features are then fed into a hybrid detection model, employing two IDCNN classifiers. The outcomes of IDCNN are obtained using an MSLF procedure which enhances the precision of depression detection. To validate the proposed MSLF-IDCNN model, comprehensive analyses, including simulation and experimental assessments are conducted.
  Keywords: depression detection; bidirectional encoder representations from transformers; improved aspect term extraction; feature extraction; modified score level fusion.
  DOI: 10.1504/IJAMECHS.2026.10077056
   
  
• A transformer-based model of fine-grained image classification for cigarette trademark identification  
  by Xiaohui Li, Haoran Zhu, Yupeng Xu, Changshen Yan, Lan Yao, Feng Zeng 
  Abstract: Traditional methods in fine-grained image recognition for cigarette trademarks have a limitation of low accuracy. In this paper, we propose a fine-grained image classification model with a transformer-based network architecture for cigarette images. In the proposed model, the local feature refinement module focuses on the critical areas of cigarette trademarks and packs via channel and spatial attention mechanisms, while the adaptive feature fusion module integrates multiscale features to enhance classification accuracy. Additionally, we design a novel loss function based on weighted cross-entropy and region sensitivity, allowing the model to focus on both global and local fine-grained features. Experimental results demonstrate that our proposed model achieves an accuracy of 99.5% on the Furongwang dataset, 98.1% on the Yuxi dataset, and 98.8% on the Liqun dataset, surpassing the best-performing existing method by up to 1.1%. These results confirm the effectiveness of our approach in the fine-grained classification of cigarette trademarks.
  Keywords: fine-grained image recognition; transformer; attention mechanism; feature fusion.
  DOI: 10.1504/IJAMECHS.2026.10076583
   
  
• Data-driven controller design in the frequency domain to achieve specified stability margin  
  by Kota Jinai, Yusuke Tsunoda, Takao Sato 
  Abstract: Data-driven control design is an effective approach for directly synthesising controllers from experimental data, without requiring explicit system identification. While tracking performance is often the primary focus, guaranteeing system stability is equally essential. Conventional data-driven design methods typically address tracking performance and stability margins separately in the time and frequency domains, respectively. However, integrating both aspects within the frequency domain offers a more coherent and practical framework. Despite its advantages, no unified method has been established to achieve this integration. This paper proposes a novel frequency-domain data-driven control design method that simultaneously ensures specified stability margins and optimises tracking performance. The proposed method enforces stability margins as constraints based on the sensitivity function, while minimising an objective function that quantifies the tracking error. Since both the objective function and constraints are formulated in the frequency domain, the proposed approach facilitates intuitive analysis of performance and robustness. Moreover, it enables a structured trade-off between control performance and stability margins through explicit specification. The effectiveness of the proposed method is demonstrated through numerical simulations comparing servo and regulator control designs.
  Keywords: frequency domain; robust stability; data-driven; trade-off design; servo; regulator.
  DOI: 10.1504/IJAMECHS.2026.10077251